INDEX

Explanations

explanations for mechanisms or phenomena in scientific studies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

InjectAttribute

-0.71

 Roskov

-0.63

 Bergh

-0.58

 AssemblyVersion

-0.55

IsContent

-0.53

Writ

-0.52

TagMode

-0.51

 beginnetje

-0.48

★★★★★

-0.48

 FormData

-0.47

POSITIVE LOGITS

 explanation

3.20

 explain

3.07

 explanations

2.91

 explaining

2.84

 explained

2.82

 explains

2.70

explanation

2.59

explain

2.56

 Explanation

2.46

 Explain

2.45

Activations Density 0.765%

explanations for mechanisms or phenomena in scientific studies

No Comments

No Known Activations